CN117436679A - Meta-universe resource matching method and system - Google Patents
Meta-universe resource matching method and system Download PDFInfo
- Publication number
- CN117436679A CN117436679A CN202311766593.8A CN202311766593A CN117436679A CN 117436679 A CN117436679 A CN 117436679A CN 202311766593 A CN202311766593 A CN 202311766593A CN 117436679 A CN117436679 A CN 117436679A
- Authority
- CN
- China
- Prior art keywords
- resource
- meta
- target user
- user
- metauniverse
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000013507 mapping Methods 0.000 claims abstract description 61
- 239000011159 matrix material Substances 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000002372 labelling Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 38
- 238000010586 diagram Methods 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000012098 association analyses Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 43
- 230000006399 behavior Effects 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 10
- 230000009466 transformation Effects 0.000 description 10
- JJWKPURADFRFRB-UHFFFAOYSA-N carbonyl sulfide Chemical compound O=C=S JJWKPURADFRFRB-UHFFFAOYSA-N 0.000 description 6
- 238000003491 array Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000007620 mathematical function Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a meta space resource matching method and a system thereof, relating to the technical field of resource matching, wherein the method comprises the following steps: acquiring each user attribute of a target user of a meta universe to be used, and labeling a corresponding attribute value; constructing an attribute matrix corresponding to the target user based on the target user attribute and the corresponding attribute value; establishing a qualitative mapping model, and analyzing the matching degree between the target user and each meta-universe resource by applying the qualitative mapping model based on the attribute matrix corresponding to the target user; and optimizing the qualitative mapping model by combining feedback of the target user on the meta-universe resource matching result. Through analysis of the demand characteristics of the target user, proper meta-universe resources are matched for the user, and according to feedback of the user on the matching result, a meta-universe matching mechanism is further optimized, so that the precision of meta-universe resource matching is gradually improved.
Description
Technical Field
The invention relates to the technical field of resource matching, in particular to a meta space resource matching method and a system thereof.
Background
Metauniverse resources refer to various entities, digitized assets, and virtual resources available for utilization and trade in the metauniverse. The meta-universe is a virtual digitized space, similar to a virtual real world, containing various virtual entities, digitized objects, virtual currency, smart contracts, and the like. Intelligent contracts are programmable contracts that execute on a blockchain and can be used to achieve automated matching of resources. Through the intelligent contracts, participants can define and enforce rules and conditions for resource matching. However, the current algorithm for resource matching has a certain bias, which is caused by the inequality and deviation existing in the historical data. If the algorithm relies solely on past data, which itself carries a bias, the result of the algorithm reflects this bias. For example, if there are gender, race, or socioeconomic differences in past resource allocations, the algorithm may continue to intensify these differences, resulting in an uneven resource allocation.
Disclosure of Invention
The invention provides a meta space resource matching method, which comprises the following steps:
step 1, obtaining each user attribute of a target user of a meta universe to be used, and labeling a corresponding attribute value;
step 2, constructing an attribute matrix corresponding to the target user based on the target user attribute and the corresponding attribute value;
step 3, establishing a qualitative mapping model, and analyzing the matching degree between the target user and each meta-universe resource by applying the qualitative mapping model based on the attribute matrix corresponding to the target user;
and 4, optimizing the qualitative mapping model by combining feedback of the target user on the meta-universe resource matching result.
The meta-universe resource matching method as described above, wherein acquiring each user attribute of a target user to be used in the meta-universe includes: user registration, questionnaires, and user behavior analysis.
A meta space resource matching method as described above, wherein the establishing of the qualitative mapping model comprises the sub-steps of:
presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the attribute matrix corresponding to the target user is arranged into a user attribute vector set;
calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
the conversion degree function is designed based on a relationship diagram between the user and the metauniverse resource.
The meta-universe resource matching method comprises the following sub-steps of:
inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
and selecting the meta space resource with the highest matching degree to match with the target user.
The meta-space resource matching method disclosed by the invention is characterized in that the qualitative mapping model is optimized by combining the feedback of a target user on the meta-space resource matching result, and specifically comprises the following sub-steps:
collecting feedback of a target user on a meta space resource matching result;
designing an objective function based on feedback of a target user on a meta space resource matching result;
and adjusting model parameters according to the meta space resource matching result and the objective function.
The invention also provides a meta space resource matching system, which comprises: the system comprises a target user attribute acquisition module, a qualitative mapping model establishment module, a metauniverse resource matching module and a metauniverse resource matching optimization module;
the target user attribute acquisition module is used for acquiring each user attribute of the target user to be used in the meta universe and labeling the corresponding attribute value;
the qualitative mapping model building module is used for building a qualitative mapping model according to the acquired target user attribute;
the meta space resource matching module is used for analyzing the matching degree between the target user and each meta space resource by applying the qualitative mapping model, and selecting the meta space resource with the highest matching degree to match with the target user;
and the metauniverse resource matching and optimizing module is used for optimizing the feedback of the qualitative mapping model to the metauniverse resource matching result by combining the target user.
The meta-universe resource matching system as described above, wherein acquiring each user attribute of a target user to be used in a meta-universe includes: user registration, questionnaires, and user behavior analysis.
A metauniverse resource matching system as described above wherein establishing a qualitative mapping model comprises the sub-steps of:
presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the attribute matrix corresponding to the target user is arranged into a user attribute vector set;
calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
the conversion degree function is designed based on a relationship diagram between the user and the metauniverse resource.
The meta-universe resource matching system as described above, wherein the qualitative mapping model is applied to analyze the matching degree between the target user and each meta-universe resource based on the attribute matrix corresponding to the target user, and specifically comprises the following sub-steps:
inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
and selecting the meta space resource with the highest matching degree to match with the target user.
The meta-space resource matching system as described above, wherein the qualitative mapping model is optimized by combining feedback of a target user on a meta-space resource matching result, specifically comprising the following sub-steps:
collecting feedback of a target user on a meta space resource matching result;
designing an objective function based on feedback of a target user on a meta space resource matching result;
and adjusting model parameters according to the meta space resource matching result and the objective function.
The beneficial effects achieved by the invention are as follows: through analysis of the demand characteristics of the target user, proper meta-universe resources are matched for the user, and according to feedback of the user on the matching result, a meta-universe matching mechanism is further optimized, so that the precision of meta-universe resource matching is gradually improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flowchart of a meta-space resource matching method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the relationship between a target user and a metauniverse resource provided by the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, a first embodiment of the present invention provides a meta-space resource matching method, including:
step S10: acquiring each user attribute of a target user of a meta universe to be used, and labeling a corresponding attribute value;
the requirements of different users on meta-universe resources are different, which may depend on the interests, professional requirements, or learning requirements of the users, and in order to understand the characteristics and requirements of the target users so as to provide them with the most suitable meta-universe experience, it is necessary to obtain the respective user attributes of the target users, where the user attributes are used to describe the user likes, and may include: age, gender, education level, profession, hobbies, consumption ability, network behavior, etc. The attribute value is a specific description of the user's attributes, for example, the age may be 18-25 years old, and the hobbies may be games, music, travel, etc.
The acquisition mode comprises three methods of user registration, questionnaire and user behavior analysis. The specific implementation mode is as follows:
(1) the user registration can be provided with real name authentication and mobile phone number binding steps, the real name authentication can acquire the gender, age and birth date of the user, and the safety of the meta universe can be enhanced; the mobile phone number can be used for short message notification and also can be directly used as a unique identifier to distinguish different users;
(2) the questionnaire is the most direct method for acquiring the user attribute, and can be set in an initialization stage before entering a meta universe, a user content initialization stage after registration or a test run stage of new content, the problems on the questionnaire can be converted into the user attribute, and the options selected by the user can be converted into attribute values;
(3) user behavior analysis is to combine different behaviors of users in meta universe to analyze and obtain user attributes;
and extracting and recording the meta-universe resource theme keywords or preset labels browsed or collected by the user as preference attributes of the user in the process of browsing or screening the meta-universe resources by the user.
Step S20: constructing an attribute matrix corresponding to the target user based on the target user attribute and the corresponding attribute value;
the user attributes and attribute values are converted into a digitized representation for subsequent computation and analysis. The attribute matrix is a two-dimensional table in which each row represents a user, each column represents an attribute, and each cell represents an attribute value. The attribute values may be represented by numbers or symbols, for example, the ages may be represented by 1-5 for different age groups, the interests may be represented by 0 or 1 for whether a certain item is liked, and the profession may be represented by different codes;
the attribute matrix corresponding to the target user is expressed as:
step S30: establishing a qualitative mapping model, and analyzing the matching degree between the target user and each meta-universe resource by applying the qualitative mapping model based on the attribute matrix corresponding to the target user;
the qualitative mapping model is an artificial intelligent model, and a relation diagram between a target user and a metauniverse resource is generated according to the attribute and the attribute value corresponding to the target user, wherein each node represents a user or a metauniverse resource, and each side represents the similarity between two nodes. The qualitative mapping model comprises a transformation degree function, wherein the transformation degree function is a mathematical function, and the matching degree between the target user and the metauniverse can be calculated according to edges in the relation diagram, so that the higher the matching degree is, the higher the matching degree between the target user and the metauniverse is. The establishment of the qualitative mapping model comprises the following sub-steps:
(1) presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the resource attributes are in one-to-one correspondence with the user attributes, and the meta-space resources after the resource attributes are preset have certain suitability, for example, the resource attributes of the meta-space resource A comprise the suitable ages under 12 years old, and the large classifications are education classes, so that the meta-space resource A is suitable for the users under 12 years old, and the use purpose is to learn.
Normalizing the resource attributes, and sorting the resource attributes into a resource attribute vector set, wherein the resource attribute vector set is expressed as:wherein r is 1 ~r z Respectively represent different meta-universe resources, B 1 ~B z Respectively represent r 1 ~r z Z is the total number of metauniverse resources,wherein ratt 1 ~ratt δ Respectively represent different resource attributes, v 1 ~v δ Respectively represent ratt 1 ~ratt δ The attribute value vector of the resource attribute, delta is the total number of the resource attributes.
(2) The attribute matrix corresponding to the target user is arranged into a user attribute vector set;
the set of user attribute vectors is expressed as:wherein u is 1 ~u n Respectively represent different target users, A 1 ~A n Respectively represent u 1 ~u n The set of attributes for the user, n is the total number of target users,wherein attr 1 ~attr m Respectively represent different user attributes, value 1 ~value m Respectively represent attr 1 ~attr m And the attribute value vector of the user attribute, m is the total number of the user attributes.
(3) Calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
the similarity function between the target user and the metauniverse resource is calculated as follows:wherein->() The formula in brackets for loop calculation j 1~z, z is the total number of metacosmic resources, ++>() The formula in brackets is used for circularly calculating i to be 1-n, n is the total number of target users, three parameters are arranged in an if () function and are separated by commas, and the expression +_ in the first parameter is used>Returning the second parameter when establishedOtherwise, returning to the third argument 0, two arguments in the corr () function, B j .ratt b Representing the b-th resource attribute, A, in the j-th meta-universe resource i .attr a An a-th user attribute representing each i-th target user, a corr () function judgment B j .ratt b And A i .attr a If the attribute is the attribute corresponding to one, returning true if yes, otherwise returning false, r j For meta-space resource with subscript j, u i For target user with subscript i, A i .value a An a-th user attribute vector for an i-th target user, B j .v b The b-th resource attribute vector of the j-th metauniverse resource;
d is a set of calculation results, after calculation, the D set contains meta-universe resources and target users with suitability, and each attribute similarity with corresponding relation between the two parties is included, and the similarity is only the similarity of each attribute between the two parties, so u in the D set is needed to be added i Term sum r j Grouping the data with the same items, and merging array elements in the group according to the grouping to obtain the overall similarity between the metauniverse resource and the target user.
The grouping formula is:wherein group () is a grouping function, two parameters are provided, comma division is used, the first parameter is grouping identification, the second parameter is grouping data, group () groups grouping data according to grouping identification, namely after converting array elements in grouping data according to the format of grouping identification (the conversion of the array element format in grouping data is only used for grouping, the output data format is the original format), grouping identification is the same and grouping is carried out, D.u l Representing the target user in the D-set with subscript l D.r l Meta-universe resource with subscript l in the D set, ++>And taking l as a connector, wherein the value of l is 1-W, W is the total number of arrays contained in the set D, and D' is the set of grouping completion.
The combining formula is:wherein D '' is the set of merge completions, +.>() For circularly calculating e, taking the formula in brackets when 1-theta, wherein theta is the number of the groups in the set D ', D'. Group e .val o Representing the similarity, D 'group, in the o-th array under the e-th group in the D' set e .u o Mu represents the weight set by the user attribute in the o-th array under the e-th group in the D' set, o takes the value of 1- ρ, and ρ is the total number of arrays contained in the group e.
(4) Establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
and connecting the metauniverse resource and the target user as nodes in the relation graph, wherein the nodes with suitability are connected, and the sides of the nodes are used as sides of the nodes to represent the similarity between the metauniverse resource and the target user, and the similarity refers to the overall similarity between the metauniverse resource and the target user.
As shown in the schematic diagram of the relationship between the target user and the metacosmic resource in FIG. 2, there are a plurality of user nodes and metacosmic resource nodes, and the user nodes and the metacosmic resource nodes connected by line segments have certain suitability, that is, the metacosmic resource nodes and the user nodes contain resource attributes and user attributes with one-to-one correspondence; the user node and the cosmic resource node are in a many-to-many relationship, that is, one cosmic resource node may adapt to a plurality of users, and one user may be interested in a plurality of cosmic resource nodes; the line segments connecting the two nodes are called edges of the nodes, and d 1-d 4 marked on the edges are the similarity between the connected nodes respectively.
(5) Designing a conversion degree function based on a relation diagram between a user and metauniverse resources;
the transformation degree function needs to transform the similarity between the metacosmic resource node and the target user node into the matching degree in the relation diagram between the user and the metacosmic resource.
The conversion degree function is expressed as:wherein->() Circularly calculating k to obtain 1-total as the formula in brackets, wherein total is the total number of edges of the calculated target user node, and d k Representing the similarity on the kth side, +.>For the conversion factor of the kth side, +.>Correction coefficients that are a function of the degree of conversion. />And->And when the system is calculated for the first time, the feedback of the meta-universe resource matching result is optimized by combining with the target user, so that the user satisfaction is improved, and MD is a matching degree set of different meta-universe resources to the target user.
The application of the qualitative mapping model analyzes the matching degree between the target user and each meta-universe resource based on the attribute matrix corresponding to the target user, and specifically comprises the following substeps:
(1) inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
(2) selecting the meta space resource with the highest matching degree to match with the target user;
the default display is the meta-universe resource with the highest matching degree, and the user can still view and select other matching items by himself.
Step S40: optimizing the qualitative mapping model by combining feedback of the target user on the meta space resource matching result;
(1) collecting feedback of a target user on a meta space resource matching result;
the feedback of the target user on the metauniverse resource matching result comprises the selection behavior of the target user on the metauniverse resource matching result and the grading of the used metauniverse resource.
(2) Designing an objective function based on feedback of a target user on a meta space resource matching result;
and carrying out association analysis on feedback of the target user on the meta-universe resource matching result and the meta-universe matching result, and after an association rule is analyzed, designing an objective function according to the association rule, wherein the objective function is expressed as:wherein p is 0 Selection mark of meta space resource with highest matching degree in matching result, p c For the selection identification of the c-th meta-universe resource in the matching result, x is the association coefficient, q c For the scoring of the c-th metauniverse resource output by the qualitative mapping model, c takes the value 1~s-1, s is the quantity of the metauniverse resource output by the qualitative mapping model, the selected identifier is only 0,1, the selected metauniverse resource is selected to be identified as 1, otherwise, the selected metauniverse resource is 0,G as the calculated matching coefficient.
(3) Adjusting model parameters according to the meta space resource matching result and the objective function;
the calculation result G of the objective function is more accurate when being closer to 1, the calculation of the meta space matching result is more accurate, the parameters of the transformation degree function in the qualitative mapping model are iterated by using a gradient descent method, the meta space resource matching result output by each parameter iteration uses the objective function to calculate the G value, and when the G value is closest to 1, the corresponding transformation degree function parameter is used as an optimal parameter and is applied to the model.
Example two
The second embodiment of the invention provides a meta space resource matching system, which comprises: the system comprises a target user attribute acquisition module, a qualitative mapping model establishment module, a metauniverse resource matching module and a metauniverse resource matching optimization module.
(1) And the target user attribute acquisition module is used for acquiring each user attribute of the target user to be used in the meta universe and labeling the corresponding attribute value.
The requirements of different users on meta-universe resources are different, which may depend on the interests, professional requirements, or learning requirements of the users, and in order to understand the characteristics and requirements of the target users so as to provide them with the most suitable meta-universe experience, it is necessary to obtain the respective user attributes of the target users, where the user attributes are used to describe the user likes, and may include: age, gender, education level, profession, hobbies, consumption ability, network behavior, etc. The attribute value is a specific description of the user's attributes, for example, the age may be 18-25 years old, and the hobbies may be games, music, travel, etc.
The acquisition mode comprises three methods of user registration, questionnaire and user behavior analysis. The specific implementation mode is as follows:
(1) the user registration can be provided with real name authentication and mobile phone number binding steps, the real name authentication can acquire the gender, age and birth date of the user, and the safety of the meta universe can be enhanced; the mobile phone number can be used for short message notification and also can be directly used as a unique identifier to distinguish different users;
(2) the questionnaire is the most direct method for acquiring the user attribute, and can be set in an initialization stage before entering a meta universe, a user content initialization stage after registration or a test run stage of new content, the problems on the questionnaire can be converted into the user attribute, and the options selected by the user can be converted into attribute values;
(3) user behavior analysis is to combine different behaviors of users in meta universe to analyze and obtain user attributes;
and extracting and recording the meta-universe resource theme keywords or preset labels browsed or collected by the user as preference attributes of the user in the process of browsing or screening the meta-universe resources by the user.
(2) And the qualitative mapping model building module is used for building a qualitative mapping model according to the acquired target user attribute.
The qualitative mapping model is an artificial intelligent model, and a relation diagram between a target user and a metauniverse resource is generated according to the attribute and the attribute value corresponding to the target user, wherein each node represents a user or a metauniverse resource, and each side represents the similarity between two nodes. The qualitative mapping model comprises a transformation degree function, wherein the transformation degree function is a mathematical function, and the matching degree between the target user and the metauniverse can be calculated according to edges in the relation diagram, so that the higher the matching degree is, the higher the matching degree between the target user and the metauniverse is. The establishment of the qualitative mapping model comprises the following sub-steps:
(1) presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the resource attributes are in one-to-one correspondence with the user attributes, and the meta-space resources after the resource attributes are preset have certain suitability, for example, the resource attributes of the meta-space resource A comprise the suitable ages under 12 years old, and the large classifications are education classes, so that the meta-space resource A is suitable for the users under 12 years old, and the use purpose is to learn.
Normalizing the resource attributes, and sorting the resource attributes into a resource attribute vector set, wherein the resource attribute vector set is expressed as:wherein r is 1 ~r z Respectively represent different meta-universe resources, B 1 ~B z Respectively represent r 1 ~r z Z is the total number of metauniverse resources,wherein ratt 1 ~ratt δ Respectively represent different resource attributes, v 1 ~v δ Respectively represent ratt 1 ~ratt δ The attribute value vector of the resource attribute, delta is the total number of the resource attributes.
(2) The attribute matrix corresponding to the target user is arranged into a user attribute vector set;
the set of user attribute vectors is expressed as:wherein u is 1 ~u n Respectively represent different target users, A 1 ~A n Respectively represent u 1 ~u n The set of attributes for the user, n is the total number of target users,wherein attr 1 ~attr m Respectively represent different user attributes, value 1 ~value m Respectively represent attr 1 ~attr m And the attribute value vector of the user attribute, m is the total number of the user attributes.
(3) Calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
the similarity formula between the target user and the metauniverse resource is calculated as follows:wherein->() The formula in brackets for loop calculation j 1~z, z is the total number of metacosmic resources, ++>() The formula in brackets is used for circularly calculating i to be 1-n, n is the total number of target users, three parameters are arranged in an if () function and are separated by commas, and the expression +_ in the first parameter is used>Returning the second parameter when establishedOtherwise, returning to the third argument 0, two arguments in the corr () function, B j .ratt b Representing the b-th resource attribute, A, in the j-th meta-universe resource i .attr a The (a) th user genus representing the (i) th target userSex, corr () function judgment B j .ratt b And A i .attr a If the attribute is the attribute corresponding to one, returning true if yes, otherwise returning false, r j For meta-space resource with subscript j, u i For target user with subscript i, A i .value a An a-th user attribute vector for an i-th target user, B j .v b The b-th resource attribute vector of the j-th metauniverse resource;
d is a set of calculation results, after calculation, the D set contains meta-universe resources and target users with suitability, and each attribute similarity with corresponding relation between the two parties is included, and the similarity is only the similarity of each attribute between the two parties, so u in the D set is needed to be added i Term sum r j Grouping the data with the same items, and merging array elements in the group according to the grouping to obtain the overall similarity between the metauniverse resource and the target user.
The grouping formula is:wherein group () is a grouping function, two parameters are provided, comma division is used, the first parameter is grouping identification, the second parameter is grouping data, group () groups grouping data according to grouping identification, namely after converting array elements in grouping data according to the format of grouping identification (the conversion of the array element format in grouping data is only used for grouping, the output data format is the original format), grouping identification is the same and grouping is carried out, D.u l Representing the target user in the D-set with subscript l D.r l Meta-universe resource with subscript l in the D set, ++>And taking l as a connector, wherein the value of l is 1-W, W is the total number of arrays contained in the set D, and D' is the set of grouping completion.
The combining formula is:wherein D '' is the set of merge completions, +.>() For circularly calculating e, taking the formula in brackets when 1-theta, wherein theta is the number of the groups in the set D ', D'. Group e .val o Representing the similarity, D 'group, in the o-th array under the e-th group in the D' set e .u o Mu represents the weight set by the user attribute in the o-th array under the e-th group in the D' set, o takes the value of 1- ρ, and ρ is the total number of arrays contained in the group e.
(4) Establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
and connecting the metauniverse resource and the target user as nodes in the relation graph, wherein the nodes with suitability are connected, and the sides of the nodes are used as sides of the nodes to represent the similarity between the metauniverse resource and the target user, and the similarity refers to the overall similarity between the metauniverse resource and the target user.
As shown in the schematic diagram of the relationship between the target user and the metacosmic resource in FIG. 2, there are a plurality of user nodes and metacosmic resource nodes, and the user nodes and the metacosmic resource nodes connected by line segments have certain suitability, that is, the metacosmic resource nodes and the user nodes contain resource attributes and user attributes with one-to-one correspondence; the user node and the cosmic resource node are in a many-to-many relationship, that is, one cosmic resource node may adapt to a plurality of users, and one user may be interested in a plurality of cosmic resource nodes; the line segments connecting the two nodes are called edges of the nodes, and d 1-d 4 marked on the edges are the similarity between the connected nodes respectively.
(5) Designing a conversion degree function based on a relation diagram between a user and metauniverse resources;
the transformation degree function needs to transform the similarity between the metacosmic resource node and the target user node into the matching degree in the relation diagram between the user and the metacosmic resource.
The conversion degree function is expressed as:wherein->() Circularly calculating k to obtain 1-total as the formula in brackets, wherein total is the total number of edges of the calculated target user node, and d k Representing the similarity on the kth side, +.>For the conversion factor of the kth side, +.>Correction coefficients that are a function of the degree of conversion. />And->And when the system is calculated for the first time, the feedback of the meta-universe resource matching result is optimized by combining with the target user, so that the user satisfaction is improved, and MD is a matching degree set of different meta-universe resources to the target user.
(3) And the metauniverse resource matching module is used for analyzing the matching degree between the target user and each metauniverse resource by applying the qualitative mapping model, and selecting the metauniverse resource with the highest matching degree to match with the target user.
(1) Inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
(2) selecting the meta space resource with the highest matching degree to match with the target user;
the default display is the meta-universe resource with the highest matching degree, and the user can still view and select other matching items by himself.
(4) And the metauniverse resource matching and optimizing module is used for optimizing the feedback of the qualitative mapping model to the metauniverse resource matching result by combining the target user.
(1) Collecting feedback of a target user on a meta space resource matching result;
the feedback of the target user on the metauniverse resource matching result comprises the selection behavior of the target user on the metauniverse resource matching result and the grading of the used metauniverse resource.
(2) Designing an objective function based on feedback of a target user on a meta space resource matching result;
and carrying out association analysis on feedback of the target user on the meta-universe resource matching result and the meta-universe matching result, and after an association rule is analyzed, designing an objective function according to the association rule, wherein the objective function is expressed as:wherein p is 0 Selection mark of meta space resource with highest matching degree in matching result, p c For the selection identification of the c-th meta-universe resource in the matching result, x is the association coefficient, q c For the scoring of the c-th metauniverse resource output by the qualitative mapping model, c takes the value 1~s-1, s is the quantity of the metauniverse resource output by the qualitative mapping model, the selected identifier is only 0,1, the selected metauniverse resource is selected to be identified as 1, otherwise, the selected metauniverse resource is 0,G as the calculated matching coefficient.
(3) Adjusting model parameters according to the meta space resource matching result and the objective function;
the calculation result G of the objective function is more accurate when being closer to 1, the calculation of the meta space matching result is more accurate, the parameters of the transformation degree function in the qualitative mapping model are iterated by using a gradient descent method, the meta space resource matching result output by each parameter iteration uses the objective function to calculate the G value, and when the G value is closest to 1, the corresponding transformation degree function parameter is used as an optimal parameter and is applied to the model.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention in further detail, and are not to be construed as limiting the scope of the invention, but are merely intended to cover any modifications, equivalents, improvements, etc. based on the teachings of the invention.
Claims (10)
1. A meta-space resource matching method, comprising:
step 1, obtaining each user attribute of a target user of a meta universe to be used, and labeling a corresponding attribute value;
step 2, constructing an attribute matrix corresponding to the target user based on the target user attribute and the corresponding attribute value;
step 3, establishing a qualitative mapping model, and analyzing the matching degree between the target user and each meta-universe resource by applying the qualitative mapping model based on the attribute matrix corresponding to the target user;
step 4, optimizing the qualitative mapping model by combining feedback of the target user on the meta space resource matching result;
optimizing the qualitative mapping model by combining the feedback of the target user on the meta-universe resource matching result, specifically comprising the following steps: collecting feedback of a target user on a meta space resource matching result; designing an objective function based on feedback of a target user on a meta-universe resource matching result, specifically performing association analysis on feedback of the target user on the meta-universe resource matching result and the meta-universe matching result, and after an association rule is analyzed, designing the objective function according to the association rule, wherein the objective function is expressed as:wherein p is 0 Selection mark of meta space resource with highest matching degree in matching result, p c For the selection identification of the c-th meta-universe resource in the matching result, x is the association coefficient, q c The value 1~s-1 is c, s is the quantity of the metauniverse resources output by the qualitative mapping model, and G is the calculated matching coefficient; and adjusting model parameters according to the meta space resource matching result and the objective function.
2. The meta-universe resource matching method of claim 1 wherein obtaining each user attribute of a target user to be used in a meta-universe comprises: user registration, questionnaires, and user behavior analysis.
3. The meta-space resource matching method according to claim 2, wherein the step of creating a qualitative mapping model comprises the sub-steps of:
presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the attribute matrix corresponding to the target user is arranged into a user attribute vector set;
calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
the conversion degree function is designed based on a relationship diagram between the user and the metauniverse resource.
4. The metauniverse resource matching method of claim 1 wherein the application of the qualitative mapping model analyzes the degree of matching between the target user and each metauniverse resource based on the attribute matrix corresponding to the target user, specifically comprising the sub-steps of:
inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
and selecting the meta space resource with the highest matching degree to match with the target user.
5. The metauniverse resource matching method of claim 4 wherein the qualitative mapping model is optimized in combination with feedback of the target user on the metauniverse resource matching result, specifically comprising the following sub-steps:
collecting feedback of a target user on a meta space resource matching result;
designing an objective function based on feedback of a target user on a meta space resource matching result;
and adjusting model parameters according to the meta space resource matching result and the objective function.
6. A metauniverse resource matching system, comprising: the system comprises a target user attribute acquisition module, a qualitative mapping model establishment module, a metauniverse resource matching module and a metauniverse resource matching optimization module;
the target user attribute acquisition module is used for acquiring each user attribute of the target user to be used in the meta universe and labeling the corresponding attribute value;
the qualitative mapping model building module is used for building a qualitative mapping model according to the acquired target user attribute;
the meta space resource matching module is used for analyzing the matching degree between the target user and each meta space resource by applying the qualitative mapping model, and selecting the meta space resource with the highest matching degree to match with the target user;
the meta-universe resource matching optimization module is used for optimizing feedback of a qualitative mapping model on a meta-universe resource matching result by combining a target user;
optimizing the qualitative mapping model in combination with the feedback of the target user on the meta-universe resource matching result specifically comprises the following steps: collecting feedback of a target user on a meta space resource matching result; designing an objective function based on feedback of a target user on a meta-universe resource matching result, specifically performing association analysis on feedback of the target user on the meta-universe resource matching result and the meta-universe matching result, and after an association rule is analyzed, designing the objective function according to the association rule, wherein the objective function is expressed as:wherein p is 0 Selection mark of meta space resource with highest matching degree in matching result, p c For the selection identification of the c-th meta-universe resource in the matching result, x is the association coefficient, q c The value 1~s-1 is c, s is the quantity of the metauniverse resources output by the qualitative mapping model, and G is the calculated matching coefficient; and adjusting model parameters according to the meta space resource matching result and the objective function.
7. The metauniverse resource matching system of claim 6 wherein obtaining individual user attributes of a target user to be used in a metauniverse comprises: user registration, questionnaires, and user behavior analysis.
8. The metauniverse resource matching system of claim 7 wherein establishing a qualitative mapping model includes the sub-steps of:
presetting resource attributes for each metauniverse resource, and sorting the resource attributes into a resource attribute vector set;
the attribute matrix corresponding to the target user is arranged into a user attribute vector set;
calculating the similarity between the target user and the metauniverse resource based on the resource attribute vector set and the user attribute vector set;
establishing a relationship diagram between a user and a metauniverse resource according to the similarity between a target user and the metauniverse resource;
the conversion degree function is designed based on a relationship diagram between the user and the metauniverse resource.
9. The metauniverse resource matching system of claim 7 wherein applying the qualitative mapping model analyzes the degree of matching between the target user and each metauniverse resource based on the attribute matrix corresponding to the target user, specifically comprising the sub-steps of:
inputting an attribute matrix corresponding to a target user into a qualitative mapping model, and calculating the matching degree between the user and different meta-universe resources;
and selecting the meta space resource with the highest matching degree to match with the target user.
10. The metaasset matching system according to claim 9, wherein the qualitative mapping model is optimized in combination with feedback of the target user on the metaasset matching result, comprising the following sub-steps:
collecting feedback of a target user on a meta space resource matching result;
designing an objective function based on feedback of a target user on a meta space resource matching result;
and adjusting model parameters according to the meta space resource matching result and the objective function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311766593.8A CN117436679B (en) | 2023-12-21 | 2023-12-21 | Meta-universe resource matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311766593.8A CN117436679B (en) | 2023-12-21 | 2023-12-21 | Meta-universe resource matching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117436679A true CN117436679A (en) | 2024-01-23 |
| CN117436679B CN117436679B (en) | 2024-03-26 |
Family
ID=89558710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311766593.8A Active CN117436679B (en) | 2023-12-21 | 2023-12-21 | Meta-universe resource matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436679B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853208A (en) * | 2024-03-07 | 2024-04-09 | 广东格利数字服务有限公司 | Digital platform intelligent deployment control method and system based on meta universe |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577579A (en) * | 2013-11-08 | 2014-02-12 | 南方电网科学研究院有限责任公司 | Resource recommendation method and system based on potential demands of users |
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| CN107833117A (en) * | 2017-12-13 | 2018-03-23 | 合肥工业大学 | A kind of Bayes's personalized ordering for considering label information recommends method |
| CN108833302A (en) * | 2018-06-27 | 2018-11-16 | 重庆邮电大学 | Resource allocation methods under cloud environment based on fuzzy clustering and stringent bipartite matching |
| CN110866687A (en) * | 2019-11-07 | 2020-03-06 | 中盈优创资讯科技有限公司 | Task allocation method and device |
| US20200104283A1 (en) * | 2018-09-27 | 2020-04-02 | Sap Se | Concurrent authoring in semantic layer universes |
| CN111124676A (en) * | 2019-12-12 | 2020-05-08 | 拉扎斯网络科技（上海）有限公司 | Resource allocation method and device, readable storage medium and electronic equipment |
| CN113159368A (en) * | 2021-01-20 | 2021-07-23 | 国电南瑞科技股份有限公司 | Power utilization model optimization method based on environment context and user feedback information |
| CN114880564A (en) * | 2022-05-17 | 2022-08-09 | 中国银行股份有限公司 | Meta-universe virtual resource recommendation method and device |
| CN115374872A (en) * | 2022-08-30 | 2022-11-22 | 中国银行股份有限公司 | Meta-universe matching method and device |
| CN115841188A (en) * | 2022-12-30 | 2023-03-24 | 北京热力智能控制技术有限责任公司 | Heat supply system supply and demand optimization method based on user behavior analysis |
| CN116843841A (en) * | 2023-09-04 | 2023-10-03 | 四川物通科技有限公司 | Large-scale virtual reality system based on grid compression |
| US11783252B1 (en) * | 2022-10-31 | 2023-10-10 | Double Diamond Interests, LLC | Apparatus for generating resource allocation recommendations |
-
2023
- 2023-12-21 CN CN202311766593.8A patent/CN117436679B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577579A (en) * | 2013-11-08 | 2014-02-12 | 南方电网科学研究院有限责任公司 | Resource recommendation method and system based on potential demands of users |
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| CN107833117A (en) * | 2017-12-13 | 2018-03-23 | 合肥工业大学 | A kind of Bayes's personalized ordering for considering label information recommends method |
| CN108833302A (en) * | 2018-06-27 | 2018-11-16 | 重庆邮电大学 | Resource allocation methods under cloud environment based on fuzzy clustering and stringent bipartite matching |
| US20200104283A1 (en) * | 2018-09-27 | 2020-04-02 | Sap Se | Concurrent authoring in semantic layer universes |
| CN110866687A (en) * | 2019-11-07 | 2020-03-06 | 中盈优创资讯科技有限公司 | Task allocation method and device |
| CN111124676A (en) * | 2019-12-12 | 2020-05-08 | 拉扎斯网络科技（上海）有限公司 | Resource allocation method and device, readable storage medium and electronic equipment |
| CN113159368A (en) * | 2021-01-20 | 2021-07-23 | 国电南瑞科技股份有限公司 | Power utilization model optimization method based on environment context and user feedback information |
| CN114880564A (en) * | 2022-05-17 | 2022-08-09 | 中国银行股份有限公司 | Meta-universe virtual resource recommendation method and device |
| CN115374872A (en) * | 2022-08-30 | 2022-11-22 | 中国银行股份有限公司 | Meta-universe matching method and device |
| US11783252B1 (en) * | 2022-10-31 | 2023-10-10 | Double Diamond Interests, LLC | Apparatus for generating resource allocation recommendations |
| CN115841188A (en) * | 2022-12-30 | 2023-03-24 | 北京热力智能控制技术有限责任公司 | Heat supply system supply and demand optimization method based on user behavior analysis |
| CN116843841A (en) * | 2023-09-04 | 2023-10-03 | 四川物通科技有限公司 | Large-scale virtual reality system based on grid compression |
Non-Patent Citations (11)
| Title |
|---|
| DAIXING ZHONG, GANGJUN YANG , JIASHUANG FAN: "A service recommendation system based on rough multidimensional matrix in cloud-based environment", COMPUTER STANDARDS & INTERFACES, vol. 82, no. 2022, 9 March 2022 (2022-03-09), pages 1 - 17, XP087022065, DOI: 10.1016/j.csi.2022.103632 * |
| HONGKAI QIU; FANG LI; ZIFENG LU; ZHIYAO ZHUANG: "Research on Resource Matching Method in Reconfigurable Intelligent Manufacturing System", 2023 9TH INTERNATIONAL CONFERENCE ON CONTROL SCIENCE AND SYSTEMS ENGINEERING (ICCSSE), 20 September 2023 (2023-09-20), pages 226 - 231 * |
| QIAOHUA HAN: "Intelligent recommendation method of literature reading based on user social network analysis", 2020 INTERNATIONAL CONFERENCE ON ROBOTS & INTELLIGENT SYSTEM (ICRIS), 6 September 2021 (2021-09-06), pages 583 - 587 * |
| WENJUN ZHU; HARRY CHANG; YANG HONG; XIANG WANG: "Hyperverse: A High Throughput Pattern Matching Engine for Metaverse", 2022 IEEE 42ND INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS WORKSHOPS (ICDCSW), 28 November 2022 (2022-11-28), pages 248 - 253 * |
| 余洋;孙林夫;任春华;韩敏: "面向多服务价值链的业务资源双边匹配模型", 计算机集成制造***, vol. 27, no. 05, 1 February 2021 (2021-02-01), pages 1397 - 1409 * |
| 店铺新人VTXK: "神经网络模型训练的用户反馈与改进策略", pages 1 - 3, Retrieved from the Internet <URL:https://wenku.***.com/view/9948240bcf22bcd126fff705cc17552706225e77.html> * |
| 张兴涛;唐文海;范林军;凌云翔;: "基于结构相似性的需求资源本体匹配方法", 计算机应用研究, vol. 32, no. 02, 27 August 2014 (2014-08-27), pages 470 - 474 * |
| 时立荣: "元宇宙空间的虚实匹配及其社会性延展", 社会科学辑刊, no. 01, 27 December 2022 (2022-12-27), pages 179 - 186 * |
| 赵晋巍;刘晓鹏;罗威;: "多匹配器自动聚合的知识图谱融合***构建", 中华医学图书情报杂志, no. 09, 15 September 2019 (2019-09-15), pages 51 - 57 * |
| 邓云，冯嘉礼: "基于定性映射的影视推荐***的应用与研究", 现代计算机(专业版), no. 05, 15 February 2014 (2014-02-15), pages 3 - 7 * |
| 邵红青, 冯嘉礼, 甘棠仪, 郑杨凡: "一种基于定性映射的自动组卷算法", 计算机辅助工程, no. 02, 15 June 2005 (2005-06-15), pages 26 - 31 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853208A (en) * | 2024-03-07 | 2024-04-09 | 广东格利数字服务有限公司 | Digital platform intelligent deployment control method and system based on meta universe |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117436679B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103761254B (en) | Method for matching and recommending service themes in various fields | |
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| CN107894998B (en) | Video recommendation method and device | |
| CN117436679B (en) | Meta-universe resource matching method and system | |
| CN108921604B (en) | Advertisement click rate prediction method based on cost-sensitive classifier integration | |
| CN104778173A (en) | Determination method, device and equipment of objective user | |
| CN110033342A (en) | A kind of training method and device, a kind of recommended method and device of recommended models | |
| CN108665148B (en) | Electronic resource quality evaluation method and device and storage medium | |
| CN110489749B (en) | Business process optimization method of intelligent office automation system | |
| CN114817663A (en) | Service modeling and recommendation method based on class perception graph neural network | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN106846082A (en) | Tourism cold start-up consumer products commending system and method based on hardware information | |
| CN110727864A (en) | User portrait method based on mobile phone App installation list | |
| CN114861050A (en) | Feature fusion recommendation method and system based on neural network | |
| CN111047406B (en) | Telecom package recommendation method, device, storage medium and equipment | |
| CN102693258A (en) | High-accuracy similarity search system | |
| Mastromarco | Foreign capital and efficiency in developing countries | |
| Afifi | Demand forecasting of short life cycle products using data mining techniques | |
| CN112925994A (en) | Group recommendation method, system and equipment based on local and global information fusion | |
| CN109977979A (en) | Position method, apparatus, electronic equipment and the storage medium of seed user | |
| Jiao et al. | An integration model for generating and selecting product configuration plans | |
| CN114266394A (en) | Enterprise portrait and scientific service personalized demand prediction method oriented to scientific service platform | |
| CN114596108A (en) | Object recommendation method and device, electronic equipment and storage medium | |
| CN113705247A (en) | Theme model effect evaluation method, device, equipment, storage medium and product | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |